Running a Large Language Model (LLM) Locally on Your Ubuntu Laptop with Ollama + GPT-OSS

Over the past year, open-weight language models have become accessible enough to run directly on consumer hardware. With the release of OpenAI’s GPT-OSS models, you no longer need cloud APIs to experiment with cutting-edge AI — you can run them locally on your own laptop.

In this post, I’ll walk you through the exact steps I used to set up and run GPT-OSS on my laptop using Ollama and Open WebUI.

Why Run an LLM Locally?

  • Privacy: your prompts and data stay on your laptop.
  • Offline use: no internet required.
  • Customization: fine-tune or extend the model for your needs.
  • Cost-control: no API calls or usage fees.

Above all, the way to play with LLM if you would like to dabble into learning how LLM are deployed and used.

Step by Step on deploying and running LLM in your laptop

? Step 1: Install Ollama

Ollama is a lightweight runtime for managing and running LLMs locally. It supports models like LLaMA, Mistral, Phi, Gemma — and now GPT-OSS.

On Linux or macOS:

curl -fsSL https://ollama.com/install.sh | sh

? Step 2: Pull and Run GPT-OSS

With Ollama running, you can pull a model. For GPT-OSS, either:

  • Use the official Ollama library when the model is listed, or
  • Import the GGUF file from Hugging Face and create a Modelfile.

First you need to pull the model into your laptop. 

ollama pull gpt-oss:latest

Now, check if the model is pulled.

ollama list

It will show all the model that is available to run in your local machine under ollama

Now run your model and then start asking questions.

ollama run gpt-oss

You should now see a REPL-like prompt where you can type questions and get answers — entirely offline. ?

You can also use browser to interact with the model but you need additional package. The best package is Open WebUI. It is only available in the Python.

? Step 3: Install Open WebUI

A terminal is fine for testing, but for a ChatGPT-like interface, we’ll use Open WebUI.

You will need to create python environment to setup the open-webui

Install with pip:

pip install open-webui

Then launch:

open-webui serve

By default, it runs at:

? http://localhost:8080

? Step 4: Connect Open WebUI to Ollama

Open WebUI auto-detects your Ollama server (default at http://localhost:11434).

  • Go to Settings ? Models in WebUI.
  • Select your GPT-OSS model (e.g., gpt-oss-20b).
  • Start chatting!

You now have a browser-based interface to your local GPT-OSS model.

? Step 5 (Optional): Enable Web Browsing

Want your local model to also search the web?

  • In Open WebUI, go to Settings ? Extensions ? Web Search.
  • Enable a search provider (DuckDuckGo, Brave, etc.).
  • Now GPT-OSS can browse live web pages and summarize them.

Conclusion

Running a model like GPT-OSS locally on a laptop would have seemed impossible just a few years ago. Today, with tools like Ollama and Open WebUI, it’s just a few commands away.

This setup is perfect for:

  • Personal productivity
  • Offline knowledge exploration
  • Experimenting with fine-tuning
  • Learning how modern LLMs work under the hood

And best of all — your data never leaves your machine.